Changeset 0.21.2 (#88)

server/database/migrations/011_v0212_workspace_chunks.sql

@@ -0,0 +1,58 @@
+-- v0.21.2: Workspace indexing + semantic search
+--
+-- New: workspace_chunks table for text embeddings per workspace file
+-- Alter: workspace_files gains index_status and chunk_count columns
+-- Alter: workspaces gains indexing_enabled column
+
+-- =========================================
+-- 1. workspace_files additions
+-- =========================================
+
+ALTER TABLE workspace_files
+    ADD COLUMN IF NOT EXISTS index_status VARCHAR(20) DEFAULT 'pending'
+        CHECK (index_status IN ('pending', 'indexing', 'ready', 'error', 'skipped'));
+
+ALTER TABLE workspace_files
+    ADD COLUMN IF NOT EXISTS chunk_count INT NOT NULL DEFAULT 0;
+
+CREATE INDEX IF NOT EXISTS idx_workspace_files_index_status
+    ON workspace_files(workspace_id, index_status)
+    WHERE index_status IN ('pending', 'indexing');
+
+-- =========================================
+-- 2. workspaces addition
+-- =========================================
+
+ALTER TABLE workspaces
+    ADD COLUMN IF NOT EXISTS indexing_enabled BOOLEAN NOT NULL DEFAULT true;
+
+-- =========================================
+-- 3. workspace_chunks table
+-- =========================================
+
+CREATE TABLE IF NOT EXISTS workspace_chunks (
+    id           UUID PRIMARY KEY DEFAULT gen_random_uuid(),
+    workspace_id UUID NOT NULL REFERENCES workspaces(id) ON DELETE CASCADE,
+    file_id      UUID NOT NULL REFERENCES workspace_files(id) ON DELETE CASCADE,
+    chunk_index  INT NOT NULL,
+    content      TEXT NOT NULL,
+    token_count  INT NOT NULL DEFAULT 0,
+    embedding    vector(3072),
+    metadata     JSONB DEFAULT '{}',
+    created_at   TIMESTAMPTZ DEFAULT NOW()
+);
+
+CREATE INDEX IF NOT EXISTS idx_workspace_chunks_file
+    ON workspace_chunks(file_id);
+
+CREATE INDEX IF NOT EXISTS idx_workspace_chunks_workspace
+    ON workspace_chunks(workspace_id);
+
+-- Note: No vector index created here. pgvector IVFFlat/HNSW indexes are
+-- limited to 2000 dimensions, but our embeddings are 3072-dim (zero-padded).
+-- Sequential scan with <=> is adequate at workspace scale (thousands of
+-- chunks, not millions). Add a partial/quantized index later if needed.
+
+COMMENT ON TABLE workspace_chunks IS 'Text chunks with vector embeddings for workspace file semantic search';
+COMMENT ON COLUMN workspace_chunks.embedding IS 'Vector embedding (3072-dim, zero-padded) for cosine similarity';
+COMMENT ON COLUMN workspace_chunks.metadata IS 'Extensible: line_start, heading, language, etc.';

server/database/migrations/sqlite/010_v0212_workspace_chunks.sql

@@ -0,0 +1,31 @@
+-- v0.21.2: Workspace indexing + semantic search (SQLite)
+
+-- workspace_files additions
+ALTER TABLE workspace_files ADD COLUMN index_status TEXT DEFAULT 'pending';
+ALTER TABLE workspace_files ADD COLUMN chunk_count INTEGER NOT NULL DEFAULT 0;
+
+CREATE INDEX IF NOT EXISTS idx_workspace_files_index_status
+    ON workspace_files(workspace_id, index_status);
+
+-- workspaces addition
+ALTER TABLE workspaces ADD COLUMN indexing_enabled INTEGER NOT NULL DEFAULT 1;
+
+-- workspace_chunks table
+-- Embeddings stored as JSON text for app-level cosine similarity.
+CREATE TABLE IF NOT EXISTS workspace_chunks (
+    id           TEXT PRIMARY KEY,
+    workspace_id TEXT NOT NULL REFERENCES workspaces(id) ON DELETE CASCADE,
+    file_id      TEXT NOT NULL REFERENCES workspace_files(id) ON DELETE CASCADE,
+    chunk_index  INTEGER NOT NULL,
+    content      TEXT NOT NULL,
+    token_count  INTEGER NOT NULL DEFAULT 0,
+    embedding    TEXT,              -- JSON array of floats
+    metadata     TEXT DEFAULT '{}', -- JSON object
+    created_at   TEXT DEFAULT (datetime('now'))
+);
+
+CREATE INDEX IF NOT EXISTS idx_workspace_chunks_file
+    ON workspace_chunks(file_id);
+
+CREATE INDEX IF NOT EXISTS idx_workspace_chunks_workspace
+    ON workspace_chunks(workspace_id);